Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a04cf7bbcbbc1a857294635ec420991d3ee3fe29f317dda881f05047852186
+oid sha256:d3f371d0cdaa78e5f0f80bf8076821fddb680f4321e463126c3e8d8b00744c66
 size 315888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e253951f0236026a0fa3ce7994d88629699058c69b24db13bb02be2c4c1ebcc8
+oid sha256:a2a4f2bd7d911cb845393f07f15eb1b376c7e711685068e08acfa92f87c7bff2
 size 450264

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd333563d341e5baa5c8b808fe012ad11a41788bafd15e1988d5d595a4760af
+oid sha256:13096529883c0adffb5e69839f0a1cd926efd800efac40df816e6ab444626905
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031735956839098696,
+  "epoch": 0.042314609118798266,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 355.283,
       "eval_steps_per_second": 88.91,
       "step": 150
+    },
+    {
+      "epoch": 0.03385168729503861,
+      "grad_norm": 0.209680438041687,
+      "learning_rate": 0.0002,
+      "loss": 10.4874,
+      "step": 160
+    },
+    {
+      "epoch": 0.035967417750978524,
+      "grad_norm": 0.1988222450017929,
+      "learning_rate": 0.0002,
+      "loss": 10.4855,
+      "step": 170
+    },
+    {
+      "epoch": 0.03808314820691844,
+      "grad_norm": 0.15512192249298096,
+      "learning_rate": 0.0002,
+      "loss": 10.4792,
+      "step": 180
+    },
+    {
+      "epoch": 0.04019887866285835,
+      "grad_norm": 0.22659450769424438,
+      "learning_rate": 0.0002,
+      "loss": 10.4735,
+      "step": 190
+    },
+    {
+      "epoch": 0.042314609118798266,
+      "grad_norm": 0.20663627982139587,
+      "learning_rate": 0.0002,
+      "loss": 10.4723,
+      "step": 200
+    },
+    {
+      "epoch": 0.042314609118798266,
+      "eval_loss": 10.472553253173828,
+      "eval_runtime": 5.5758,
+      "eval_samples_per_second": 356.902,
+      "eval_steps_per_second": 89.315,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 25040624025600.0,
+  "total_flos": 33387498700800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null