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:c2380e3e61e092a89679dee80363b0adb64c1fc1367184fe86777c27f051f472
+oid sha256:6804b423ab579eac14abfe4a914746b5787222a8c5002b9bfcb979a342b3b30b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e9e4ab7e1ff6348b65d587eef953867a36c6f6ad772d71bc6b842a7871d63c
+oid sha256:edb758723c8a090c620920b81781b67cfa1d34a1913cc9e4b83a08c4bf5b030e
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c103f85206916bbddbfdec4d0ebb18b19e3d0dd8d88c9b4c12898c57e206a7e
+oid sha256:0c72461d8b102f8348796119289aad1a7993b551f980fac40ec203302a5c72e0
 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": 0.28929068150208626,
+  "epoch": 0.4339360222531293,
   "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": 6.976,
       "eval_steps_per_second": 3.488,
       "step": 26
+    },
+    {
+      "epoch": 0.3004172461752434,
+      "grad_norm": 0.2234642058610916,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.6434,
+      "step": 27
+    },
+    {
+      "epoch": 0.31154381084840055,
+      "grad_norm": 0.28918102383613586,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.6914,
+      "step": 28
+    },
+    {
+      "epoch": 0.3226703755215577,
+      "grad_norm": 0.211372509598732,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.6567,
+      "step": 29
+    },
+    {
+      "epoch": 0.3337969401947149,
+      "grad_norm": 0.275553822517395,
+      "learning_rate": 5e-05,
+      "loss": 0.5738,
+      "step": 30
+    },
+    {
+      "epoch": 0.34492350486787204,
+      "grad_norm": 0.34773099422454834,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.7286,
+      "step": 31
+    },
+    {
+      "epoch": 0.3560500695410292,
+      "grad_norm": 0.22577843070030212,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.6837,
+      "step": 32
+    },
+    {
+      "epoch": 0.3671766342141864,
+      "grad_norm": 0.29821667075157166,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.7444,
+      "step": 33
+    },
+    {
+      "epoch": 0.37830319888734354,
+      "grad_norm": 0.23734945058822632,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.627,
+      "step": 34
+    },
+    {
+      "epoch": 0.3894297635605007,
+      "grad_norm": 0.22903797030448914,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8233,
+      "step": 35
+    },
+    {
+      "epoch": 0.40055632823365783,
+      "grad_norm": 0.29000309109687805,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.5556,
+      "step": 36
+    },
+    {
+      "epoch": 0.41168289290681503,
+      "grad_norm": 0.2623641788959503,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.7741,
+      "step": 37
+    },
+    {
+      "epoch": 0.4228094575799722,
+      "grad_norm": 0.21798746287822723,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6794,
+      "step": 38
+    },
+    {
+      "epoch": 0.4339360222531293,
+      "grad_norm": 0.28965574502944946,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.6445,
+      "step": 39
+    },
+    {
+      "epoch": 0.4339360222531293,
+      "eval_loss": 0.7118078470230103,
+      "eval_runtime": 21.7647,
+      "eval_samples_per_second": 6.984,
+      "eval_steps_per_second": 3.492,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.543125549805732e+17,
+  "total_flos": 2.3146883247085978e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null