Training in progress, step 80, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f71b0b5e651bfa43394de1ec7d8428077bfb7952f3a083a9d13225c0cd9012
+size 2433024

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b38bb8abb3d220538758ca4d6c8f252b4e4de441a427b163fa2aed268470a3
+size 2498406

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09467455621301775,
+  "eval_steps": 20,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001183431952662722,
+      "eval_loss": 11.929322242736816,
+      "eval_runtime": 3.6693,
+      "eval_samples_per_second": 409.34,
+      "eval_steps_per_second": 25.618,
+      "step": 1
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 0.19140625,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 11.9299,
+      "step": 10
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 11.9289,
+      "step": 20
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "eval_loss": 11.92916488647461,
+      "eval_runtime": 3.6752,
+      "eval_samples_per_second": 408.685,
+      "eval_steps_per_second": 25.577,
+      "step": 20
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 0.251953125,
+      "learning_rate": 4.8e-05,
+      "loss": 11.9288,
+      "step": 30
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 11.9293,
+      "step": 40
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "eval_loss": 11.928914070129395,
+      "eval_runtime": 3.578,
+      "eval_samples_per_second": 419.785,
+      "eval_steps_per_second": 26.272,
+      "step": 40
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 0.373046875,
+      "learning_rate": 8e-05,
+      "loss": 11.9265,
+      "step": 50
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.158203125,
+      "learning_rate": 9.6e-05,
+      "loss": 11.9267,
+      "step": 60
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 11.92799186706543,
+      "eval_runtime": 3.6694,
+      "eval_samples_per_second": 409.333,
+      "eval_steps_per_second": 25.617,
+      "step": 60
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 0.146484375,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 11.9275,
+      "step": 70
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 11.9256,
+      "step": 80
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "eval_loss": 11.925419807434082,
+      "eval_runtime": 3.5672,
+      "eval_samples_per_second": 421.062,
+      "eval_steps_per_second": 26.351,
+      "step": 80
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 31380406272.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c89f6448937446d20e02bf21f83a5fa21acdb9b00d5542967c76a39de32304
+size 6712