Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39c8fc9c1d6149b070a6a481ff3e91e494e6ba22454ac9dc3d799dac47d42e1
+oid sha256:6bcee9918630476b949e88866730d4a6e86b8c927babdbe7adbdba9e24318aae
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14cb582215ed6d0b4d511f8db0660dadf04fbbcfec00e1e8a5a6c65260f2744
+oid sha256:18f3d0083d1fe1c58cd5630cfb52c5e597edbc660833f1f06f851f7689297475
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007189072609633358,
+  "epoch": 0.0011981787682722263,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 386.294,
       "eval_steps_per_second": 193.202,
       "step": 6
+    },
+    {
+      "epoch": 0.0008387251377905584,
+      "grad_norm": 0.14451463520526886,
+      "learning_rate": 0.00014,
+      "loss": 10.8327,
+      "step": 7
+    },
+    {
+      "epoch": 0.000958543014617781,
+      "grad_norm": 0.17358613014221191,
+      "learning_rate": 0.00016,
+      "loss": 10.8334,
+      "step": 8
+    },
+    {
+      "epoch": 0.0010783608914450035,
+      "grad_norm": 0.13881893455982208,
+      "learning_rate": 0.00018,
+      "loss": 10.8354,
+      "step": 9
+    },
+    {
+      "epoch": 0.0010783608914450035,
+      "eval_loss": 10.837157249450684,
+      "eval_runtime": 9.1743,
+      "eval_samples_per_second": 383.137,
+      "eval_steps_per_second": 191.623,
+      "step": 9
+    },
+    {
+      "epoch": 0.0011981787682722263,
+      "grad_norm": 0.23394715785980225,
+      "learning_rate": 0.0002,
+      "loss": 10.8405,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 492177457152.0,
+  "total_flos": 820295761920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null