Training in progress, step 13600, checkpoint

last-checkpoint/README.md

@@ -1295,6 +1295,10 @@ You can finetune this model on your own dataset.
 | 0.2350 | 13300 | 0.3857        |
 | 0.2359 | 13350 | 0.3555        |
 | 0.2368 | 13400 | 0.381         |
+| 0.2377 | 13450 | 0.3804        |
+| 0.2386 | 13500 | 0.3666        |
+| 0.2394 | 13550 | 0.3792        |
+| 0.2403 | 13600 | 0.3341        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ff219d2dc182bff9938951ac2d922c87f8b3382fe905eda8bb33e8c98eb346
+oid sha256:4084e1bfff0b99538c5f3a28b4d5c1e1e185739ef9b70378a9c51e1850e71288
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe0f24feef012ade435d0955f499b908ca4147d4a231048c8182b66d61b6f43
+oid sha256:1d8dc4ebf2f928553dc4ad0074e5667a33bafb03875d3b2cedcef46264b4d6a1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c735c57cb6abf0ceb0d281a7f9e69dc9a61b723c825d122108ee089e4f92d40
+oid sha256:51aa928f18dc099dd2a30735dc4332b9f48a48dd04ae86490c1e2444ca246dd2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578b0f8cd0a36e27a4c0005bc9769962acef123517226f60d74acf957afcc72c
+oid sha256:979320729f9d3865290bdaaad2a8c03ebcf3b70e0f3a530f818585a8c564617e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54be013f521e475446bbdac4929f2f53d5e8b1200009f671ab53144a213230f
+oid sha256:2936671a733ca2c04f8afa89dc17be4e7bd4f657d12145bb68896d055120fca2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23678676821402697,
+  "epoch": 0.24032089908289303,
   "eval_steps": 500,
-  "global_step": 13400,
+  "global_step": 13600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1884,6 +1884,34 @@
       "learning_rate": 4.240442952229487e-05,
       "loss": 0.381,
       "step": 13400
+    },
+    {
+      "epoch": 0.23767030093124347,
+      "grad_norm": 3.011683225631714,
+      "learning_rate": 4.2355343503956335e-05,
+      "loss": 0.3804,
+      "step": 13450
+    },
+    {
+      "epoch": 0.23855383364846,
+      "grad_norm": 3.5077691078186035,
+      "learning_rate": 4.23062574856178e-05,
+      "loss": 0.3666,
+      "step": 13500
+    },
+    {
+      "epoch": 0.23943736636567653,
+      "grad_norm": 2.875953197479248,
+      "learning_rate": 4.225717146727926e-05,
+      "loss": 0.3792,
+      "step": 13550
+    },
+    {
+      "epoch": 0.24032089908289303,
+      "grad_norm": 2.3432717323303223,
+      "learning_rate": 4.220808544894073e-05,
+      "loss": 0.3341,
+      "step": 13600
     }
   ],
   "logging_steps": 50,