Training in progress, step 2620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0fe0e9d900d8fecd195e1a719802ba1ac5f49e274f580b73f4466c3f57dd5c
+oid sha256:09f4952dfa3428aca2c1575fa34747e5f6666aaf7e2613abd8099507cce9d64f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed18925aeed2c70e87f6e85275b0e2e7c1d48fcea3988e938200f4125c88c46
+oid sha256:aa2dc1feaa27f4960c5b987e34d3adacdc59e0bd9286eb375d733edcb69b45b2
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a353eb9058a377bea13c7e9eeff43101bb2c4a8b11951234da6a710bb5053f86
+oid sha256:c5151ca7e89138bc5e58bcff1bca431f336f49a4dbf5210fb5304f6ccdc5f5fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e63d6cbad437bb2ff0881a0f3731290a112af9056e30047c433328ae16fc214
+oid sha256:0393290c0ec4f4951317a3da41220b93fbef7d67af7626ecc076b5555bdbb9a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9302325581395349,
+  "epoch": 0.9373881932021467,
   "eval_steps": 500,
-  "global_step": 2600,
+  "global_step": 2620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2087,14 +2087,30 @@
       "loss": 0.386,
       "num_input_tokens_seen": 1762187,
       "step": 2600
+    },
+    {
+      "epoch": 0.9338103756708408,
+      "grad_norm": 0.26331019401550293,
+      "learning_rate": 1.3237924865831844e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 1769463,
+      "step": 2610
+    },
+    {
+      "epoch": 0.9373881932021467,
+      "grad_norm": 0.3325729966163635,
+      "learning_rate": 1.2522361359570662e-05,
+      "loss": 0.4048,
+      "num_input_tokens_seen": 1777203,
+      "step": 2620
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1762187,
+  "num_input_tokens_seen": 1777203,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.96253626569257e+16,
+  "total_flos": 3.996301946954342e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null