Training in progress, step 8600, checkpoint

last-checkpoint/README.md

@@ -1193,6 +1193,10 @@ You can finetune this model on your own dataset.
 | 0.1467 | 8300 | 0.3967        |
 | 0.1475 | 8350 | 0.4911        |
 | 0.1484 | 8400 | 0.4076        |
+| 0.1493 | 8450 | 0.398         |
+| 0.1502 | 8500 | 0.4203        |
+| 0.1511 | 8550 | 0.414         |
+| 0.1520 | 8600 | 0.3436        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4889319c3ce656b4822f1a50aac0284145a17b11d2f3ae21fabab4cf0583b0e
+oid sha256:03eb7a5af20bd02ca3c82b2b9c70071b68c323ac87a7799ea87cd5139a94eb91
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef06c105348a65b7eed64942f5dea6f43606f7f0ef5b2b0bde7930b99c26cac5
+oid sha256:40262b6becfc7b5455f773e7a9a3bb594892eb51a5604b32e91c90609a89bdfb
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d487123f633c1d3c5f62a2fbd2d4a814f21aa207d5180464abde74c25ff991
+oid sha256:66f5a47fc1fb0afabfab2902b2aa5af7ab84c4d2097ab2d93b83ccc74c03acb1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899a642947e70d7e60cf2eeee96b1e912dfb435fbf6e019478dc646f870906c8
+oid sha256:b161abd57fc77c436995db62a6c89b28c6220f59213ab301dd9a979ea4c14232
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d81eef3cd79f288260f908a6802f0ede97e49007282e07a31f47a48189a183b
+oid sha256:f6c145ff6cd9415e52757f69b1d04fadde604f73651764ac12eda7fa02fc8ae0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1484334964923751,
+  "epoch": 0.1519676273612412,
   "eval_steps": 500,
-  "global_step": 8400,
+  "global_step": 8600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1184,6 +1184,34 @@
       "learning_rate": 4.731106791541497e-05,
       "loss": 0.4076,
       "step": 8400
+    },
+    {
+      "epoch": 0.14931702920959164,
+      "grad_norm": 2.1234054565429688,
+      "learning_rate": 4.7261981897076444e-05,
+      "loss": 0.398,
+      "step": 8450
+    },
+    {
+      "epoch": 0.15020056192680814,
+      "grad_norm": 2.1532113552093506,
+      "learning_rate": 4.72128958787379e-05,
+      "loss": 0.4203,
+      "step": 8500
+    },
+    {
+      "epoch": 0.15108409464402467,
+      "grad_norm": 1.8909550905227661,
+      "learning_rate": 4.7163809860399366e-05,
+      "loss": 0.414,
+      "step": 8550
+    },
+    {
+      "epoch": 0.1519676273612412,
+      "grad_norm": 1.9415462017059326,
+      "learning_rate": 4.711472384206083e-05,
+      "loss": 0.3436,
+      "step": 8600
     }
   ],
   "logging_steps": 50,