Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7658a3a06b21302132ffdb3c44677163c62a841c6a75937c29942cce0735a8c3
-size 1020304
+oid sha256:f63b7401d6f1f053dafd113e09af67725b58a90ee651f882b7b24a7ae624677f
+size 1442155488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f08148518dd75c6cb3c33284322975095a7f4e0ae38ae90e6858945411687b
-size 2050100
+oid sha256:99bb53e19ef6ae8d533c317034f43a15e1a71989d60a33361f86e0b67a99dedc
+size 2884319911

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a254765eec0dbfa31d8135a8fcc3798d70e595f5e2fb78755568cbc5d77c54bc
-size 13990
+oid sha256:bc057f3c42a7f268a03e1c2cbf4efada08801fa84e6b247630c5d5aebe7a49e0
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c45ca3da33995233b317a52bbb54883b007b0ee672f560754ead8c070de158
-size 1064
+oid sha256:673b41d82e959aac00dcaee03910aa1ae8fec244a3f68516132c0a2a2c133a42
+size 623

last-checkpoint/trainer_state.json

@@ -1,86 +1,30 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 100,
+  "epoch": 0.4,
+  "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.0009933333333333333,
-      "loss": 107.9679,
-      "step": 100
-    },
-    {
-      "epoch": 0.2,
-      "eval_loss": 107.60591888427734,
-      "eval_runtime": 2.9012,
-      "eval_samples_per_second": 2757.093,
-      "eval_steps_per_second": 344.68,
-      "step": 100
-    },
     {
       "epoch": 0.4,
       "learning_rate": 0.0009866666666666667,
-      "loss": 107.299,
-      "step": 200
-    },
-    {
-      "epoch": 0.4,
-      "eval_loss": 107.40342712402344,
-      "eval_runtime": 2.9018,
-      "eval_samples_per_second": 2756.548,
-      "eval_steps_per_second": 344.612,
-      "step": 200
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00098,
-      "loss": 107.1292,
-      "step": 300
-    },
-    {
-      "epoch": 0.6,
-      "eval_loss": 107.37178802490234,
-      "eval_runtime": 2.9469,
-      "eval_samples_per_second": 2714.362,
-      "eval_steps_per_second": 339.338,
-      "step": 300
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.0009733333333333334,
-      "loss": 107.2419,
-      "step": 400
-    },
-    {
-      "epoch": 0.8,
-      "eval_loss": 107.33102416992188,
-      "eval_runtime": 2.8354,
-      "eval_samples_per_second": 2821.132,
-      "eval_steps_per_second": 352.686,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.0009666666666666667,
-      "loss": 106.8579,
+      "loss": 604775687127.04,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 107.2762680053711,
-      "eval_runtime": 2.7905,
-      "eval_samples_per_second": 2866.49,
-      "eval_steps_per_second": 358.356,
+      "epoch": 0.4,
+      "eval_loss": 131995.421875,
+      "eval_runtime": 1160.1962,
+      "eval_samples_per_second": 17.238,
+      "eval_steps_per_second": 2.155,
       "step": 500
     }
   ],
-  "logging_steps": 100,
-  "max_steps": 15000,
+  "logging_steps": 500,
+  "max_steps": 37500,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 500,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd82f6e1773f6a7d02e870eb55078322cbc39e495a7405cd6543c01ec1cde80b
-size 4664
+oid sha256:3b7299bf524f1973f62b60202b64e7bc80a078785ee25db337292dcbcc00155e
+size 4207