Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff540b9931ff3b9051aa7ca25e64a8e24ca7e8526e26bc089bc76ac294f8b424
+oid sha256:e05637d9fe00567351aebe30b8907548391539066a69466b08d62fb0de2c8b6a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a063f1bf8d5647653d13d9d67ef96e737ad0d45a0be438a667d109a536c16697
+oid sha256:fd2dde3b7d6cb9a958c80e4da86c9ac7e84d7b0aad33d337c26e27372676e0e8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b330fcd1c4b02a2985ceb253ae804bf16171e108be502780a5eab9132fe8fd30
+oid sha256:5ac6d446adeddd129c374743386b9fda911e1104accc0a9ad12d81db0a9913ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2d50ca5391f126ee8cc2961637b87c22247c1f8f80ebd7b00bac4d79271141
+oid sha256:6e468fb4a523a6bf7dace3eac71fcc8bc1ed6b95078548573228e864e9505bcd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08158940076828003,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 2.32,
+  "epoch": 2.4,
   "eval_steps": 500,
-  "global_step": 14500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2269,6 +2269,84 @@
       "eval_samples_per_second": 17.144,
       "eval_steps_per_second": 2.143,
       "step": 14500
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 7419.63623046875,
+      "learning_rate": 6.72e-06,
+      "loss": 0.0527,
+      "step": 14550
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 6152.6513671875,
+      "learning_rate": 6.64e-06,
+      "loss": 0.048,
+      "step": 14600
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 6703.68994140625,
+      "learning_rate": 6.560000000000001e-06,
+      "loss": 0.0537,
+      "step": 14650
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 8612.31640625,
+      "learning_rate": 6.48e-06,
+      "loss": 0.0512,
+      "step": 14700
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 6183.3798828125,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.0499,
+      "step": 14750
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 7795.396484375,
+      "learning_rate": 6.3200000000000005e-06,
+      "loss": 0.0525,
+      "step": 14800
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 6911.2099609375,
+      "learning_rate": 6.2399999999999995e-06,
+      "loss": 0.0503,
+      "step": 14850
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 9744.9267578125,
+      "learning_rate": 6.16e-06,
+      "loss": 0.0509,
+      "step": 14900
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 4487.8115234375,
+      "learning_rate": 6.08e-06,
+      "loss": 0.0504,
+      "step": 14950
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 6276.47607421875,
+      "learning_rate": 6e-06,
+      "loss": 0.0505,
+      "step": 15000
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.08178989589214325,
+      "eval_runtime": 116.6529,
+      "eval_samples_per_second": 17.145,
+      "eval_steps_per_second": 2.143,
+      "step": 15000
     }
   ],
   "logging_steps": 50,
@@ -2288,7 +2366,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.063911530496e+16,
+  "total_flos": 7.30749468672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null