Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775a33c89d1507553a33ff8920d44b3f69461471d464c47e7836f43531f3c8eb
+oid sha256:af7516424eed61f8f1e54610a1236a86697c8e44fb3f1c809dbf4beb5baa347a
 size 11638960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73b25ccc1cadf73889fd5332b04bdfa13f8c82d7cd43c170d66b44faaf662f0
+oid sha256:cfc44b11b001de020855a4e015bbed613e23f501164a31f2b7f7ba1e81ddce0b
 size 20673175

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97efec430ccccc0dbfae1f6a038ecb0173d0b0fd1277d0783c90e147589dde65
+oid sha256:eaa3b8bb8bf1579708f41366c051dcff2d32629dfa5761a94099908e021e4487
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45b6d2f2b103ddcb3038fa6b31fcae5b5e27115a1219ac35631b093c941b2a8
+oid sha256:f523c687f0caf80d904a00ff35d9c05e3338e5b3dfd49f11fb88db038ba76be3
 size 623

last-checkpoint/trainer_state.json

@@ -1,62 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019457524224617658,
-  "eval_steps": 500,
-  "global_step": 1500,
+  "epoch": 0.012971682816411773,
+  "eval_steps": 1000,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.01,
-      "learning_rate": 9.935141585917941e-05,
-      "loss": 0.4454,
-      "step": 500
-    },
-    {
-      "epoch": 0.01,
-      "eval_loss": 0.43116331100463867,
-      "eval_runtime": 44.1341,
-      "eval_samples_per_second": 965.806,
-      "eval_steps_per_second": 120.746,
-      "step": 500
-    },
     {
       "epoch": 0.01,
       "learning_rate": 9.870283171835882e-05,
-      "loss": 0.4372,
+      "loss": 0.4413,
       "step": 1000
     },
     {
       "epoch": 0.01,
       "eval_loss": 0.4252806007862091,
-      "eval_runtime": 44.2641,
-      "eval_samples_per_second": 962.969,
-      "eval_steps_per_second": 120.391,
+      "eval_runtime": 44.1153,
+      "eval_samples_per_second": 966.218,
+      "eval_steps_per_second": 120.797,
       "step": 1000
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 9.805424757753824e-05,
-      "loss": 0.4307,
-      "step": 1500
-    },
-    {
-      "epoch": 0.02,
-      "eval_loss": 0.4136431813240051,
-      "eval_runtime": 44.2019,
-      "eval_samples_per_second": 964.324,
-      "eval_steps_per_second": 120.56,
-      "step": 1500
     }
   ],
-  "logging_steps": 500,
+  "logging_steps": 1000,
   "max_steps": 77091,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 500,
-  "total_flos": 287882132544000.0,
+  "save_steps": 1000,
+  "total_flos": 191921421696000.0,
   "train_batch_size": 8,
   "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:d111f3ca5d4704711f5a74c01bdd0af34272b2915b56acd587f2482f22c7231d
+oid sha256:73d8f77ae3f372c2a4869ecfb95a0437ca524feaab3e3fbe3a1efa4cac16640e
 size 4271