Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37478746c85b8723d14dcbb2fc4735af4afdba95b4e5e90986fca9bd6f23e674
+oid sha256:5092df653a241c295e8a40fe8a5653dd9db368600a132fc9f1bacfdd9186d561
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366c336029a0f38e1629b855cfa5e67d773414585cb779ff11b841a5b42f2e47
+oid sha256:f2697522f49692aec26ba5936d226adf0d45a6ceb6e239b4eab00ec454a7416c
 size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6844cd586de68a6e1a4752382bd60051acd338bfb31d133b33aba14fbb697dfc
+oid sha256:c6c3cdbf034ef9f86029f99db82daec670863e67518e294d6fbac9a3fc658d9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd7876a5529313f948bdc210083cf5735b238914ddd6881d9bbdbd82ae856f5
+oid sha256:601daa59fb095b2a4822edf3d826c0c91406d982679fa2815535f957a5251e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027609055770292656,
+  "epoch": 0.030676728633658508,
   "eval_steps": 20,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,51 @@
       "eval_samples_per_second": 5.084,
       "eval_steps_per_second": 0.661,
       "step": 440
+    },
+    {
+      "epoch": 0.028222590342965825,
+      "grad_norm": 0.7773933410644531,
+      "learning_rate": 0.00019813875480651232,
+      "loss": 1.5046,
+      "step": 460
+    },
+    {
+      "epoch": 0.028222590342965825,
+      "eval_loss": 1.4094576835632324,
+      "eval_runtime": 19.6378,
+      "eval_samples_per_second": 5.092,
+      "eval_steps_per_second": 0.662,
+      "step": 460
+    },
+    {
+      "epoch": 0.029449659488312168,
+      "grad_norm": 0.6018341779708862,
+      "learning_rate": 0.0001980569418309744,
+      "loss": 1.508,
+      "step": 480
+    },
+    {
+      "epoch": 0.029449659488312168,
+      "eval_loss": 1.396529197692871,
+      "eval_runtime": 19.7008,
+      "eval_samples_per_second": 5.076,
+      "eval_steps_per_second": 0.66,
+      "step": 480
+    },
+    {
+      "epoch": 0.030676728633658508,
+      "grad_norm": 0.6028321981430054,
+      "learning_rate": 0.00019797512885543647,
+      "loss": 1.5018,
+      "step": 500
+    },
+    {
+      "epoch": 0.030676728633658508,
+      "eval_loss": 1.3898202180862427,
+      "eval_runtime": 19.7395,
+      "eval_samples_per_second": 5.066,
+      "eval_steps_per_second": 0.659,
+      "step": 500
     }
   ],
   "logging_steps": 20,
@@ -344,7 +389,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 2.917888490999808e+16,
+  "total_flos": 3.228714037020672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null