Training in progress, step 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348fe87f7d0e8b1a386eea2e19f99b6ac25b18da8f4f7647f3a312340b114664
+oid sha256:4ad3613ef0ee29ca86146fd428cc0c1e08f6ddbc4972d2688ba40754f03cde58
 size 3086634632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab111018e14f3e9a82317c5072d4909563856f09fc058284c0d2f49a069d0a72
+oid sha256:d5c778279cf29494c876bb2e645da0a4341624e2f6a834a563dd661fcdfb1650
 size 3136004290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c481b071ec751916e215a2646c6e9c49fcf402da6c4a4d0804bdf05f0c57cec
+oid sha256:da0a5b26cef0a5106af3505cd537cb0ccd25d37dca9d04aeb79f08ffc4d4dd01
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c2566492d307f81e4c3ec55ad3d6c8b63efc28d7dcd132e6f5f82a7a7b3840
+oid sha256:7b400d8747cfb55081da1a0068eee816c4d961918098df38f1b9b55162e6473d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a0c31b135429597fb4601695aee5de28b0f5fb6a2c4e45d278a9e4001d0c26
+oid sha256:f6cd997f499454e13ac4dabde7c9b3fae456372bd14cee40bac36217d9c8b4b1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7027027027027026,
+  "epoch": 4.054054054054054,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 40.846,
       "eval_steps_per_second": 2.068,
       "step": 100
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 0.9624,
+      "step": 110
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00019809681293474693,
+      "loss": 0.4856,
+      "step": 120
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00019746884336284317,
+      "loss": 0.4526,
+      "step": 130
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00019675278913395606,
+      "loss": 0.4579,
+      "step": 140
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 0.4416,
+      "step": 150
+    },
+    {
+      "epoch": 4.054054054054054,
+      "eval_loss": 3.037287473678589,
+      "eval_runtime": 36.5611,
+      "eval_samples_per_second": 41.055,
+      "eval_steps_per_second": 2.079,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.220293195661312e+16,
+  "total_flos": 4.830439793491968e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null