Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141d191f9bcdd39498885915e2d7bf96dc38ff085252131d7bd08be492816295
+oid sha256:7ef890e1ce7ec1e435c4d670477c72d5aa9bad60f1a9f06d349e84bd03b253e7
 size 360740440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c772caae67d55adf1aa3ea85c6d9ed81553d6c46659205586afb92f72bde4b0a
+oid sha256:198cd135c7fe764ee6c77aa7e7e28bb3ae4f593f133ff611a891a30332c8485a
 size 183437434

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4c94d61c3ff7e2b6da38686f75fef06f47c982b0440552f825bd0ad032e8d8
+oid sha256:5e4e0b01dbca4264fff7a579e7726d984002dcfda26f82111da49515b0c5f976
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776f3b3c5ca619117b7ec3591ad6146e3460cc91e36840c57746b92eb33808c8
+oid sha256:ef5216b0ff262075a1d16c8a63cd384b25153b98ad619964d9a0822a7e9a2a00
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9ae16719f0d7ac09a68c9054d9c7d34ecab86b65b2cc5d030a6e6848b99552
+oid sha256:58de60e69e8c777ff21fc5db8b5ad2688e8e8a584a528d031eab34d70ea08b27
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22c625348c29a092cbcb39c50c37993a1f14e8e54ec0961044f5491ab3b380b
+oid sha256:52255fdc2995ab7c43dd88021eede5e2047551d7334d5a62c411ac3ff005e077
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdf50bcd205bcced00afd16da79d01c2658d1493dd016830f975a5b6e2d7e3b
+oid sha256:47df95fae6b0a761442bbe91ed7012d62713ff1c3e78f64eee5c1c29c87ec242
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9809402795425668,
+  "epoch": 2.0304955527318933,
   "eval_steps": 160,
-  "global_step": 1560,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1179,6 +1179,42 @@
       "learning_rate": 1.7077534966650766e-07,
       "loss": 0.0003,
       "step": 1560
+    },
+    {
+      "epoch": 1.9936467598475223,
+      "grad_norm": 0.0017273375997319818,
+      "learning_rate": 9.60850767065924e-08,
+      "loss": 0.0003,
+      "step": 1570
+    },
+    {
+      "epoch": 2.0050825921219824,
+      "grad_norm": 0.002094059018418193,
+      "learning_rate": 4.2712080634949024e-08,
+      "loss": 0.0003,
+      "step": 1580
+    },
+    {
+      "epoch": 2.017789072426938,
+      "grad_norm": 0.025685803964734077,
+      "learning_rate": 1.0679160603449534e-08,
+      "loss": 0.0003,
+      "step": 1590
+    },
+    {
+      "epoch": 2.0304955527318933,
+      "grad_norm": 0.0016396486898884177,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0304955527318933,
+      "eval_loss": 0.00027946667978540063,
+      "eval_runtime": 7.4081,
+      "eval_samples_per_second": 101.915,
+      "eval_steps_per_second": 5.13,
+      "step": 1600
     }
   ],
   "logging_steps": 10,
@@ -1193,12 +1229,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.076629852516516e+17,
+  "total_flos": 4.1811588230938624e+17,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null