Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993bef54891e9f26928b34290e6027d8c9c9ce4065d79d42ca7be3baf1070577
+oid sha256:37478746c85b8723d14dcbb2fc4735af4afdba95b4e5e90986fca9bd6f23e674
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5659b524e48a2f03547e258274127e7efcfbbf02c56da73569563c1781b871
+oid sha256:366c336029a0f38e1629b855cfa5e67d773414585cb779ff11b841a5b42f2e47
 size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e45582261b53d7ecaa35c88e1eccb7713c6d0eb5a23b772caf206808bfa0b5
+oid sha256:6844cd586de68a6e1a4752382bd60051acd338bfb31d133b33aba14fbb697dfc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40873409734f7d9ee90459df93f961e6509fa0a5626c33d9d437e5203db441a6
+oid sha256:7dd7876a5529313f948bdc210083cf5735b238914ddd6881d9bbdbd82ae856f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024541382906926805,
+  "epoch": 0.027609055770292656,
   "eval_steps": 20,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,36 @@
       "eval_samples_per_second": 5.063,
       "eval_steps_per_second": 0.658,
       "step": 400
+    },
+    {
+      "epoch": 0.025768452052273145,
+      "grad_norm": 0.8461142778396606,
+      "learning_rate": 0.00019830238075758816,
+      "loss": 1.5175,
+      "step": 420
+    },
+    {
+      "epoch": 0.025768452052273145,
+      "eval_loss": 1.4290988445281982,
+      "eval_runtime": 19.703,
+      "eval_samples_per_second": 5.075,
+      "eval_steps_per_second": 0.66,
+      "step": 420
+    },
+    {
+      "epoch": 0.026995521197619485,
+      "grad_norm": 0.7308184504508972,
+      "learning_rate": 0.00019822056778205025,
+      "loss": 1.4878,
+      "step": 440
+    },
+    {
+      "epoch": 0.026995521197619485,
+      "eval_loss": 1.4188473224639893,
+      "eval_runtime": 19.6677,
+      "eval_samples_per_second": 5.084,
+      "eval_steps_per_second": 0.661,
+      "step": 440
     }
   ],
   "logging_steps": 20,
@@ -314,7 +344,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 2.60309133775872e+16,
+  "total_flos": 2.917888490999808e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null