Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c914af7e4717984588deb34667879d37816d8425bf9f40c7f2df62411adc325a
+oid sha256:3ffbf8790409dcc7f8ae4e5a4966c936a38f8b35fdd2d824e7615da66bc2eed9
 size 4140280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1d4cc7e69b6d4ecabbbf7997c661f2f6b544b7bb70ab8878c1272f23010f6f
+oid sha256:40cdddd868b8628780578eafdc62f083f38c7191db137d46765fb42910c21aa2
 size 4291766

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4651e32e118f1ea1a8e26dfbbe64298593e12e6a71bcd36cb77f04f86d3f86d
+oid sha256:02bd6697dd0ac01f79967d93e880e93c5ad7e5d6a672668dd596f9f42c435066
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c1eba909fbb51daca773a25c075f182b4096aff21c9b4ff19dbada2080ac99
+oid sha256:1946c0d35865c02655624537450071d8e3a581f1d24f3c539357cae293b3d2d2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28adb9f06e220aefdc723ea4380a84d42b8bfb87cc53ce65859d55ce1876f51c
+oid sha256:a9faf933c304288a566e09316737d2bdccb42e76da4138d98110982bcbf5dbf1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423c49ed521f6986d20d8b29112b383f4b0f3f2e228084ef82c2ad7dcd5d1de8
+oid sha256:2f2cb6de5c0f2b78c1515e90a9ab03144587d336dd27fc87023f09785c5d64cb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
+oid sha256:84f22729b765b6841bd185712dd3ab8bf338866cd8396b5dce62f9950913691a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.666666666666668,
-  "eval_steps": 200,
-  "global_step": 100,
+  "epoch": 3.3333333333333335,
+  "eval_steps": 20,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,9 +11,9 @@
     {
       "epoch": 0.16666666666666666,
       "eval_loss": 10.377338409423828,
-      "eval_runtime": 2.3495,
-      "eval_samples_per_second": 638.849,
-      "eval_steps_per_second": 5.107,
+      "eval_runtime": 2.3538,
+      "eval_samples_per_second": 637.683,
+      "eval_steps_per_second": 5.098,
       "step": 1
     },
     {
@@ -31,67 +31,19 @@
       "step": 20
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 0.45703125,
-      "learning_rate": 0.00016772815716257412,
-      "loss": 10.2229,
-      "step": 30
-    },
-    {
-      "epoch": 6.666666666666667,
-      "grad_norm": 0.458984375,
-      "learning_rate": 0.00014016954246529696,
-      "loss": 10.1217,
-      "step": 40
-    },
-    {
-      "epoch": 8.333333333333334,
-      "grad_norm": 0.4609375,
-      "learning_rate": 0.00010825793454723325,
-      "loss": 10.0382,
-      "step": 50
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.4609375,
-      "learning_rate": 7.54514512859201e-05,
-      "loss": 9.9768,
-      "step": 60
-    },
-    {
-      "epoch": 11.666666666666666,
-      "grad_norm": 0.4609375,
-      "learning_rate": 4.530518418775733e-05,
-      "loss": 9.9373,
-      "step": 70
-    },
-    {
-      "epoch": 13.333333333333334,
-      "grad_norm": 0.462890625,
-      "learning_rate": 2.1085949060360654e-05,
-      "loss": 9.9182,
-      "step": 80
-    },
-    {
-      "epoch": 15.0,
-      "grad_norm": 0.46484375,
-      "learning_rate": 5.418275829936537e-06,
-      "loss": 9.9122,
-      "step": 90
-    },
-    {
-      "epoch": 16.666666666666668,
-      "grad_norm": 0.462890625,
-      "learning_rate": 0.0,
-      "loss": 9.9115,
-      "step": 100
+      "epoch": 3.3333333333333335,
+      "eval_loss": 10.274003028869629,
+      "eval_runtime": 2.365,
+      "eval_samples_per_second": 634.681,
+      "eval_steps_per_second": 5.074,
+      "step": 20
     }
   ],
   "logging_steps": 10,
   "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 17,
-  "save_steps": 200,
+  "save_steps": 20,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -99,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 164363029708800.0,
+  "total_flos": 32872605941760.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767cbb0126f5e19779e9fcc2851f3166d36ca132f2aa13429b17ffa28b07b942
+oid sha256:fa3a4fef869eec54885a3e827a7faceb53e864a7600488a249371d1dec63ce95
 size 6904