Training in progress, step 3474, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f933b839b39d4ea5b711a39c3d96e083669ab787323d2c3a263e59741c3418
+oid sha256:357ae939fcb410e6b99ec86035610dd8f49a84dae7f3c1295d149581f4b6ffb7
 size 678616072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31cce8802518823cbba6378d69472af5cc920225c511639f6968237303ab8ca
+oid sha256:72fcabc7f0556c4da51ab570b31d9ac89d55fdf7aa1fe0bd18bfdabd1928148b
 size 35918620

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e35f27c0e810ea2c4295eb8b934526418c1259a8125586d1614dbc4bfed6cb5
+oid sha256:cc1b6b8e868013db57c0396ae7239b53f297d3c4d8ffddd8e9eb89d144075c78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4dd0bd6be37524d79857f9676dd6ba4b10d38ff5759d1470f3d5532961ebb3
+oid sha256:bfd16bd47d2a528ae4a16d4e28b182d543a83fa480feb06c902c23c3b7635e47
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.181347150259067,
+  "epoch": 6.0,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 3474,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,34 @@
       "eval_samples_per_second": 7.731,
       "eval_steps_per_second": 0.969,
       "step": 3000
+    },
+    {
+      "epoch": 5.354058721934369,
+      "grad_norm": 3.369074821472168,
+      "learning_rate": 6.287827841291191e-06,
+      "loss": 2.342,
+      "step": 3100
+    },
+    {
+      "epoch": 5.526770293609672,
+      "grad_norm": 3.664003610610962,
+      "learning_rate": 4.606590450571621e-06,
+      "loss": 2.3859,
+      "step": 3200
+    },
+    {
+      "epoch": 5.699481865284974,
+      "grad_norm": 3.5953192710876465,
+      "learning_rate": 2.9253530598520513e-06,
+      "loss": 2.3374,
+      "step": 3300
+    },
+    {
+      "epoch": 5.872193436960276,
+      "grad_norm": 3.2417404651641846,
+      "learning_rate": 1.2441156691324815e-06,
+      "loss": 2.3414,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
@@ -252,12 +280,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.896375584768e+16,
+  "total_flos": 1.030161330487296e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null