Training in progress, step 45200, checkpoint

last-checkpoint/README.md

@@ -1193,6 +1193,10 @@ You can finetune this model on your own dataset.
 | 0.7934 | 44900 | 0.3381        |
 | 0.7943 | 44950 | 0.2914        |
 | 0.7952 | 45000 | 0.282         |
+| 0.7961 | 45050 | 0.2596        |
+| 0.7969 | 45100 | 0.311         |
+| 0.7978 | 45150 | 0.2368        |
+| 0.7987 | 45200 | 0.3147        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef76b6fee8c0fd9556900a05eb0770041bcc5a9708508b78f491641cac655f8
+oid sha256:f7bc1279cf26374bbe94542da62a9c0d4afab0f4ba7ae70859bbcb9c9a68dd05
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb08a5d8f04e486ccde9a85e4e9299751359a9d9614ffc3531e3deafb4e0a876
+oid sha256:c01262363633d3d77ce1db0dfb29f97a979fcb51db6af60308b261c77050d227
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e372030ae72b97fbc6cc5e639f35bf2df20cbde1f7751bd5565217fb58eec7
+oid sha256:3b37a75ff2cf38c26a23d005c931008fab38bb3848944732097424886cc09ed5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c78515125dc6571e473b9ee78fd09306ea3ef81a3f639c80068abccc6924eae
+oid sha256:7508f8a8b4fb4d80e6e1cbe138ce75da05ff3779ab0aeb5d7b1f2c4f9795a0eb
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8371b7f9012f9b7db42f400823445baf760f1582673ba8da16f0fa77bea3fc99
+oid sha256:229878378d7cc80eb5eb56eb236e5a16279538f082126201a0410ceb9d7b9c95
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7951794454948666,
+  "epoch": 0.7987135763637327,
   "eval_steps": 500,
-  "global_step": 45000,
+  "global_step": 45200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6308,6 +6308,34 @@
       "learning_rate": 1.1396791737841392e-05,
       "loss": 0.282,
       "step": 45000
+    },
+    {
+      "epoch": 0.7960629782120832,
+      "grad_norm": 1.1699323654174805,
+      "learning_rate": 1.1347705719502857e-05,
+      "loss": 0.2596,
+      "step": 45050
+    },
+    {
+      "epoch": 0.7969465109292997,
+      "grad_norm": 1.4282245635986328,
+      "learning_rate": 1.129861970116432e-05,
+      "loss": 0.311,
+      "step": 45100
+    },
+    {
+      "epoch": 0.7978300436465162,
+      "grad_norm": 1.4583613872528076,
+      "learning_rate": 1.1249533682825785e-05,
+      "loss": 0.2368,
+      "step": 45150
+    },
+    {
+      "epoch": 0.7987135763637327,
+      "grad_norm": 1.3440780639648438,
+      "learning_rate": 1.120044766448725e-05,
+      "loss": 0.3147,
+      "step": 45200
     }
   ],
   "logging_steps": 50,