Training in progress, step 550, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9edd40202ee9bdf83a9f4827636fe20841088385d615033eadefca3bdaa0d7
+oid sha256:8385203f596de8aec071a817af0a90618943345118234c81496a6d709ac0cad2
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd03f6f393ff738690b65d3fe4979497863b808868e53b447f27f154a47f61e0
+oid sha256:86f7cafbda4990666498942d2dd48605dbce42584dc23356fe53d3e68303cde0
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c381572d32a65fc1a155eecfa512281a474c4a471f1632383ddae55b8849c5e3
+oid sha256:49b680b85eae2177a0e3c70b0083e23e76610b8562b9aef882c92452ea1cadba
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b5691046896d865f067a1958689168fc2411c74d2f82d596bd6a636b2b141b
+oid sha256:b0b8a6e3878f9402461193b241d8f1ee8546c6ad03f43e5b9dab8f4fc8c4d065
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5924175694b6d639a07e1869835f8c2275afefcb042e767ca76a1976be92d591
+oid sha256:e3372cb7b685e225287edc953534a919d443ed17283851ec6045c9673db22615
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.03123048094940662,
+  "epoch": 0.034353529044347283,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -446,6 +446,49 @@
       "eval_samples_per_second": 14.886,
       "eval_steps_per_second": 14.886,
       "step": 500
+    },
+    {
+      "epoch": 0.03185509056839475,
+      "grad_norm": 958464.0,
+      "learning_rate": 0.024682675930095266,
+      "loss": 8.2639,
+      "step": 510
+    },
+    {
+      "epoch": 0.03247970018738289,
+      "grad_norm": 2483027968.0,
+      "learning_rate": 0.02388970125104685,
+      "loss": 8.0817,
+      "step": 520
+    },
+    {
+      "epoch": 0.03310430980637102,
+      "grad_norm": 2.386907802506363e+17,
+      "learning_rate": 0.02309784454872262,
+      "loss": 9.0499,
+      "step": 530
+    },
+    {
+      "epoch": 0.033728919425359154,
+      "grad_norm": 225280.0,
+      "learning_rate": 0.022307903155699027,
+      "loss": 7.8657,
+      "step": 540
+    },
+    {
+      "epoch": 0.034353529044347283,
+      "grad_norm": 1171456.0,
+      "learning_rate": 0.02152067247599837,
+      "loss": 7.8539,
+      "step": 550
+    },
+    {
+      "epoch": 0.034353529044347283,
+      "eval_loss": 7.987682819366455,
+      "eval_runtime": 56.3279,
+      "eval_samples_per_second": 14.966,
+      "eval_steps_per_second": 14.966,
+      "step": 550
     }
   ],
   "logging_steps": 10,
@@ -460,7 +503,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 10
+        "early_stopping_patience_counter": 11
       }
     },
     "TrainerControl": {
@@ -474,7 +517,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.04231081984e+16,
+  "total_flos": 2.246541901824e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null