Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d174b3637de775d72604b2f466a7e2730c31f8bbe42288320db515c38494cafd
+oid sha256:3d751c5b027e9bd168cf97bc8ac2e14ed984bdc5ea43713bf9ac7b00ce0d9734
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e5df9ecd18c0c5d4aee7cd4c5038c63f72caeac62b83817ba101e575cb0c0d
+oid sha256:c98c9228780b5154dd4a1b891bcbd30fb9379b77dba5d7b5c8cf81d27cb539ab
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08898395721925134,
+  "epoch": 0.133475935828877,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 28.219,
       "eval_steps_per_second": 14.138,
       "step": 26
+    },
+    {
+      "epoch": 0.09240641711229947,
+      "grad_norm": 0.732320249080658,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.5086,
+      "step": 27
+    },
+    {
+      "epoch": 0.09582887700534759,
+      "grad_norm": 0.6814180016517639,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.5471,
+      "step": 28
+    },
+    {
+      "epoch": 0.09925133689839573,
+      "grad_norm": 0.7060202956199646,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.3652,
+      "step": 29
+    },
+    {
+      "epoch": 0.10267379679144385,
+      "grad_norm": 0.9559823274612427,
+      "learning_rate": 5e-05,
+      "loss": 0.8032,
+      "step": 30
+    },
+    {
+      "epoch": 0.10609625668449198,
+      "grad_norm": 1.1005346775054932,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.8232,
+      "step": 31
+    },
+    {
+      "epoch": 0.1095187165775401,
+      "grad_norm": 0.7558871507644653,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.5147,
+      "step": 32
+    },
+    {
+      "epoch": 0.11294117647058824,
+      "grad_norm": 0.6404812932014465,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.4,
+      "step": 33
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.8565809726715088,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5938,
+      "step": 34
+    },
+    {
+      "epoch": 0.11978609625668449,
+      "grad_norm": 0.6082307696342468,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4025,
+      "step": 35
+    },
+    {
+      "epoch": 0.12320855614973263,
+      "grad_norm": 0.7612841725349426,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.5164,
+      "step": 36
+    },
+    {
+      "epoch": 0.12663101604278074,
+      "grad_norm": 0.7494601011276245,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.442,
+      "step": 37
+    },
+    {
+      "epoch": 0.1300534759358289,
+      "grad_norm": 0.6392002701759338,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.2912,
+      "step": 38
+    },
+    {
+      "epoch": 0.133475935828877,
+      "grad_norm": 0.7933446168899536,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.3706,
+      "step": 39
+    },
+    {
+      "epoch": 0.133475935828877,
+      "eval_loss": 0.5577317476272583,
+      "eval_runtime": 17.4945,
+      "eval_samples_per_second": 28.18,
+      "eval_steps_per_second": 14.119,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7497924728586240.0,
+  "total_flos": 1.124688709287936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null