Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10af7548fb8c6868868d9117a697aa679c3b0a9545c5004dc4ff4ed618cdab3f
+oid sha256:9d8bb98cc079647c8595486d7ec4c6c1dbfeab5c9d69b725689294cc7970fea7
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53b2446ef82e9f2a7a956a150f27de962d9e6722be49d09df036310a4de37c4
+oid sha256:c45325f5b31a2e0c27b39dfa70d3fa45e24543d4239b3ca7c2adb32ea06e4cba
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ee482f5b2fd848da1cf5054146921d698d37b6ef63d8e74f41d283a0f13b84
+oid sha256:356b548ab3e5c18278417ebb5318355e9481c8992b11479d08e62a1cb33f7930
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010265359544218037,
+  "epoch": 0.020530719088436074,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 23.833,
       "eval_steps_per_second": 11.922,
       "step": 50
+    },
+    {
+      "epoch": 0.012318431453061643,
+      "grad_norm": 0.47477608919143677,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.315,
+      "step": 60
+    },
+    {
+      "epoch": 0.014371503361905251,
+      "grad_norm": 0.526182234287262,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.3055,
+      "step": 70
+    },
+    {
+      "epoch": 0.016424575270748858,
+      "grad_norm": 0.6147613525390625,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.3017,
+      "step": 80
+    },
+    {
+      "epoch": 0.018477647179592466,
+      "grad_norm": 0.6105421781539917,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.3058,
+      "step": 90
+    },
+    {
+      "epoch": 0.020530719088436074,
+      "grad_norm": 0.5068532228469849,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.2953,
+      "step": 100
+    },
+    {
+      "epoch": 0.020530719088436074,
+      "eval_loss": 0.2939603924751282,
+      "eval_runtime": 86.3176,
+      "eval_samples_per_second": 23.761,
+      "eval_steps_per_second": 11.886,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.140578662219776e+16,
+  "total_flos": 2.254755040591872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null