Training in progress, step 20, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fdf89f0fd7dd6fbe9eeacac4a67aa119b62a3a4e0bb2532c080fcaaa3927fa
+oid sha256:a9a1b5fe74d30a2b57275019644a375677da441d563a6cd3de6fb409ded03f62
 size 4956450288

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f17a270ec2582d3b80ca44646e38c1190ad03af747fc0196f9aa1f5b4ad2196
+oid sha256:77f31d93e3f4bb89019d604b40346ff6e1fc555bbf740c89dc528ba7e5a1fa13
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243666f1190af6ded0e54e42649b5282ba9c715d9bcc56b00f78ffd8c0cfff34
+oid sha256:b4ffc2a19903049d433ee79e54f725e3f6a735e76cfecc66c0f6c64d4acad3d3
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ffbd45539607b0e8b66094865a0f7f706b47ca1ed1a4ec5be6fc18e090daa0
-size 14512
+oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5f77331c015c2fd3688f154dd7d064d1e00e5484711314e9f0b3e2e863b085
-size 14512
+oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
+size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e85371deea3100d2ab445c982136740c600243d9badeb6e5c72c07324d88a6c
+oid sha256:86a562280f18454416a11d2a32a1435679f44d10b11637c5297815c06d499163
 size 1064

last-checkpoint/trainer_state.json

@@ -1,199 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6666666666666665,
-  "eval_steps": 50,
-  "global_step": 200,
+  "epoch": 0.5405405405405406,
+  "eval_steps": 20,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.013333333333333334,
+      "epoch": 0.02702702702702703,
       "eval_loss": 3.1186463832855225,
-      "eval_runtime": 41.9099,
-      "eval_samples_per_second": 35.815,
-      "eval_steps_per_second": 3.603,
+      "eval_runtime": 21.1695,
+      "eval_samples_per_second": 70.904,
+      "eval_steps_per_second": 3.59,
       "step": 1
     },
     {
-      "epoch": 0.13333333333333333,
-      "grad_norm": 4.875,
-      "learning_rate": 3.6363636363636364e-05,
-      "loss": 2.2677,
+      "epoch": 0.2702702702702703,
+      "grad_norm": 6.0,
+      "learning_rate": 8e-05,
+      "loss": 2.1439,
       "step": 10
     },
     {
-      "epoch": 0.26666666666666666,
-      "grad_norm": 3.03125,
-      "learning_rate": 7.272727272727273e-05,
-      "loss": 1.9172,
+      "epoch": 0.5405405405405406,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00016,
+      "loss": 1.9251,
       "step": 20
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 2.390625,
-      "learning_rate": 0.00010909090909090909,
-      "loss": 1.9044,
-      "step": 30
-    },
-    {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 1.859375,
-      "learning_rate": 0.00014545454545454546,
-      "loss": 1.9292,
-      "step": 40
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 2.15625,
-      "learning_rate": 0.00018181818181818183,
-      "loss": 2.0171,
-      "step": 50
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "eval_loss": 1.9083219766616821,
-      "eval_runtime": 40.4746,
-      "eval_samples_per_second": 37.085,
-      "eval_steps_per_second": 3.731,
-      "step": 50
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 1.7421875,
-      "learning_rate": 0.00019998870284726968,
-      "loss": 2.0829,
-      "step": 60
-    },
-    {
-      "epoch": 0.9333333333333333,
-      "grad_norm": 1.921875,
-      "learning_rate": 0.00019989834093992945,
-      "loss": 2.1828,
-      "step": 70
-    },
-    {
-      "epoch": 1.0666666666666667,
-      "grad_norm": 2.390625,
-      "learning_rate": 0.00019971769878721743,
-      "loss": 1.7834,
-      "step": 80
-    },
-    {
-      "epoch": 1.2,
-      "grad_norm": 15.9375,
-      "learning_rate": 0.00019944693963927092,
-      "loss": 1.4227,
-      "step": 90
-    },
-    {
-      "epoch": 1.3333333333333333,
-      "grad_norm": 10.0,
-      "learning_rate": 0.00019908630818686338,
-      "loss": 1.4005,
-      "step": 100
-    },
-    {
-      "epoch": 1.3333333333333333,
-      "eval_loss": 2.2226054668426514,
-      "eval_runtime": 40.4748,
-      "eval_samples_per_second": 37.085,
-      "eval_steps_per_second": 3.731,
-      "step": 100
-    },
-    {
-      "epoch": 1.4666666666666668,
-      "grad_norm": 5.15625,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 1.4408,
-      "step": 110
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 1.875,
-      "learning_rate": 0.00019809681293474693,
-      "loss": 1.318,
-      "step": 120
-    },
-    {
-      "epoch": 1.7333333333333334,
-      "grad_norm": 2.234375,
-      "learning_rate": 0.00019746884336284317,
-      "loss": 1.3544,
-      "step": 130
-    },
-    {
-      "epoch": 1.8666666666666667,
-      "grad_norm": 1.8828125,
-      "learning_rate": 0.00019675278913395606,
-      "loss": 1.4563,
-      "step": 140
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 4.59375,
-      "learning_rate": 0.00019594929736144976,
-      "loss": 1.4406,
-      "step": 150
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.1810431480407715,
-      "eval_runtime": 54.0552,
-      "eval_samples_per_second": 27.768,
-      "eval_steps_per_second": 2.793,
-      "step": 150
-    },
-    {
-      "epoch": 2.1333333333333333,
-      "grad_norm": 2.078125,
-      "learning_rate": 0.00019505909417784754,
-      "loss": 0.7759,
-      "step": 160
-    },
-    {
-      "epoch": 2.2666666666666666,
-      "grad_norm": 4.59375,
-      "learning_rate": 0.00019408298407861042,
-      "loss": 0.7577,
-      "step": 170
-    },
-    {
-      "epoch": 2.4,
-      "grad_norm": 3.234375,
-      "learning_rate": 0.00019302184919509755,
-      "loss": 0.7745,
-      "step": 180
-    },
-    {
-      "epoch": 2.533333333333333,
-      "grad_norm": 1.796875,
-      "learning_rate": 0.0001918766484973654,
-      "loss": 0.7984,
-      "step": 190
-    },
-    {
-      "epoch": 2.6666666666666665,
-      "grad_norm": 1.8125,
-      "learning_rate": 0.0001906484169275263,
-      "loss": 0.8212,
-      "step": 200
-    },
-    {
-      "epoch": 2.6666666666666665,
-      "eval_loss": 2.586805582046509,
-      "eval_runtime": 42.7073,
-      "eval_samples_per_second": 35.146,
-      "eval_steps_per_second": 3.536,
-      "step": 200
+      "epoch": 0.5405405405405406,
+      "eval_loss": 1.7902483940124512,
+      "eval_runtime": 21.3533,
+      "eval_samples_per_second": 70.294,
+      "eval_steps_per_second": 3.559,
+      "step": 20
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1100,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
-  "save_steps": 50,
+  "num_train_epochs": 14,
+  "save_steps": 20,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -206,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.819283858358272e+16,
+  "total_flos": 1.3638567716716544e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a097d8f6050774249bd291d7596e77b256195d2e9dca6b13a05d78fe71f26a2
+oid sha256:a3f334277fb93a403ef7fd7cac6f2e3db7ca0d17bb46fbd3f915c745d20e4c8e
 size 9144