Training in progress, step 2740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d5da627a83cc018d4bf0bfc59c1098cf129633a1abc41bd7d51fb13114c0b1
+oid sha256:8d9e8b32b966f871c511b5657fa29716b505e3b46707edada57780def8a3a4f0
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682f21df5b619b8fc7a877dafd3f697aa66e4f2b393f8b846f0e3646f7ba1e83
+oid sha256:09d1dd512e5173901c2f4b3e632283257f9e9c5e3f7e6ab6ae19723b4371d0b6
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdb4aa20ae8b96f35fdee422b168c0d1ffe465638f08b59f076576138bbe18e
+oid sha256:91283a9e0978c1c4026d0596abe9afca642afabfe3852b23f40302b2b4a58b48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6164b3c850dce9a36a31f30919cac3506bfad9cadb5f9ef73ee2c76d96b38ff
+oid sha256:8a07583ff04916149d2b98a04a5a3645539e81ed096b0a41ed14e70c156517bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2128,
+  "epoch": 0.2192,
   "eval_steps": 500,
-  "global_step": 2660,
+  "global_step": 2740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -938,6 +938,34 @@
       "learning_rate": 2.9173085201008144e-05,
       "loss": 3.5365,
       "step": 2660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 26.394916534423828,
+      "learning_rate": 2.9157103476060547e-05,
+      "loss": 3.5944,
+      "step": 2680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 23.64137077331543,
+      "learning_rate": 2.914097324979651e-05,
+      "loss": 3.5048,
+      "step": 2700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 35.18840408325195,
+      "learning_rate": 2.9124694691414485e-05,
+      "loss": 3.5769,
+      "step": 2720
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 25.55812644958496,
+      "learning_rate": 2.9108267971668828e-05,
+      "loss": 3.5082,
+      "step": 2740
     }
   ],
   "logging_steps": 20,
@@ -945,7 +973,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6299096079630336.0,
+  "total_flos": 6492126069227520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null