Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c504859f80703c359b50c8b9eaa3e53c7cbb854cedcc2da33fd05a11a38d9b
+oid sha256:842c1300dd3b9fe18a7c694c66d942930870600894c8a083566b4589017654c0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e54de63a3133fa32dfb094c45f51e2d08788e68382955c0e896c21826c38b7
+oid sha256:de25e8dc83e96e1bef10b7af746402cd07605c8553e5361003806dd0004b42c8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c420e03dec32abc624a0a882554eeb54d2163094dbb50f1943f056f39d83cb
+oid sha256:49c5acd72411d5d34f9e74b8b5ece59aeb9e89cf6df34020e29b1378650b3d7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d71d2520220b24b14e74f15b8fc66bb3fd91884b9f80b2d1815e9fc2c23c
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019598236158745713,
+  "epoch": 0.039196472317491425,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,87 @@
       "eval_samples_per_second": 10.801,
       "eval_steps_per_second": 2.713,
       "step": 20
+    },
+    {
+      "epoch": 0.020578147966683,
+      "grad_norm": 3.4481372833251953,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 1.8509,
+      "step": 21
+    },
+    {
+      "epoch": 0.023517883390494855,
+      "grad_norm": 2.712968349456787,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7398,
+      "step": 24
+    },
+    {
+      "epoch": 0.02449779519843214,
+      "eval_loss": 0.8747045993804932,
+      "eval_runtime": 39.8105,
+      "eval_samples_per_second": 10.801,
+      "eval_steps_per_second": 2.713,
+      "step": 25
+    },
+    {
+      "epoch": 0.02645761881430671,
+      "grad_norm": 3.010244846343994,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 1.7664,
+      "step": 27
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "grad_norm": 2.739521026611328,
+      "learning_rate": 0.0001,
+      "loss": 1.7532,
+      "step": 30
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "eval_loss": 0.8650626540184021,
+      "eval_runtime": 39.8003,
+      "eval_samples_per_second": 10.804,
+      "eval_steps_per_second": 2.714,
+      "step": 30
+    },
+    {
+      "epoch": 0.03233708966193043,
+      "grad_norm": 2.8129777908325195,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.8224,
+      "step": 33
+    },
+    {
+      "epoch": 0.034296913277805,
+      "eval_loss": 0.8579776287078857,
+      "eval_runtime": 39.8042,
+      "eval_samples_per_second": 10.803,
+      "eval_steps_per_second": 2.713,
+      "step": 35
+    },
+    {
+      "epoch": 0.035276825085742286,
+      "grad_norm": 3.0579378604888916,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6987,
+      "step": 36
+    },
+    {
+      "epoch": 0.03821656050955414,
+      "grad_norm": 2.4026262760162354,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.5442,
+      "step": 39
+    },
+    {
+      "epoch": 0.039196472317491425,
+      "eval_loss": 0.8561304807662964,
+      "eval_runtime": 39.8087,
+      "eval_samples_per_second": 10.802,
+      "eval_steps_per_second": 2.713,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -103,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.406258997362688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null