Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c0237246514adf5ea646e9d3c5381f47f6089dba19cf8ef74896aa770b6a33
+oid sha256:ecb5c6cd61430b4f248fd40e9cc6bf89af8a7c0cf3e736d4b267030cb33950db
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553efc9b62ce11fb610699a192aff54a140782f5550dc9c0a145425c292fd21e
+oid sha256:1a969d9d32bb414b34eb063c5b95b9c6cce5e490437f19bf178799b86ff03c9a
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004705172673804856,
+  "epoch": 0.006032272658724174,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 298.884,
       "eval_steps_per_second": 149.442,
       "step": 39
+    },
+    {
+      "epoch": 0.004825818126979339,
+      "grad_norm": 0.7044286131858826,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 44.3988,
+      "step": 40
+    },
+    {
+      "epoch": 0.004946463580153823,
+      "grad_norm": 0.6289908289909363,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 44.4344,
+      "step": 41
+    },
+    {
+      "epoch": 0.0050671090333283065,
+      "grad_norm": 0.7178926467895508,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 44.4319,
+      "step": 42
+    },
+    {
+      "epoch": 0.00518775448650279,
+      "grad_norm": 0.6604595184326172,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 44.414,
+      "step": 43
+    },
+    {
+      "epoch": 0.005308399939677274,
+      "grad_norm": 0.6216382384300232,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 44.4595,
+      "step": 44
+    },
+    {
+      "epoch": 0.005429045392851757,
+      "grad_norm": 0.6452557444572449,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 44.4258,
+      "step": 45
+    },
+    {
+      "epoch": 0.005549690846026241,
+      "grad_norm": 0.7613912224769592,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 44.4296,
+      "step": 46
+    },
+    {
+      "epoch": 0.005670336299200724,
+      "grad_norm": 0.7586554288864136,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 44.4294,
+      "step": 47
+    },
+    {
+      "epoch": 0.005790981752375207,
+      "grad_norm": 0.5697535872459412,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 44.392,
+      "step": 48
+    },
+    {
+      "epoch": 0.005911627205549691,
+      "grad_norm": 0.6201058626174927,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 44.4235,
+      "step": 49
+    },
+    {
+      "epoch": 0.006032272658724174,
+      "grad_norm": 0.7422836422920227,
+      "learning_rate": 0.0,
+      "loss": 44.5028,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 638968135680.0,
+  "total_flos": 822219374592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null