Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c168fa0f116989b170154e76ec0898286a04c2e1af3ea3161ad289960edf97
+oid sha256:0a4926c85de91288fe6f06d97b943f1271f14965c6a45e5489ff1160a470a4d7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdf15d8b8656ca11bc48e6f5273b1f300891766789fad867f4904b0b40ec7ee
+oid sha256:f644afaeb35592d20ad4050dfcaa12c4bd8176c898486644fac6d4587756ac88
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a829795ae4aa5ec8c28fed9b536a5ef82d18cf59b2900944a50f9f8310c506c
+oid sha256:0403941aa6de2eb4baf35cb227f7f96455fada34654996d73ae5e536d2760774
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001516374954034884,
+  "epoch": 0.003032749908069768,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.728,
       "eval_steps_per_second": 2.728,
       "step": 25
+    },
+    {
+      "epoch": 0.001819649944841861,
+      "grad_norm": 1.9589847326278687,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6359,
+      "step": 30
+    },
+    {
+      "epoch": 0.002122924935648838,
+      "grad_norm": 1.4695641994476318,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6006,
+      "step": 35
+    },
+    {
+      "epoch": 0.002426199926455815,
+      "grad_norm": 1.7299948930740356,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6185,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027294749172627917,
+      "grad_norm": 1.8927239179611206,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.586,
+      "step": 45
+    },
+    {
+      "epoch": 0.003032749908069768,
+      "grad_norm": 1.600250482559204,
+      "learning_rate": 0.0,
+      "loss": 1.4815,
+      "step": 50
+    },
+    {
+      "epoch": 0.003032749908069768,
+      "eval_loss": NaN,
+      "eval_runtime": 21453.8519,
+      "eval_samples_per_second": 2.732,
+      "eval_steps_per_second": 2.732,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.41887283560448e+16,
+  "total_flos": 1.483774567120896e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null