Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d435ce0de6012fb4236c06060f6cf69269f2b1360a5d6aa435758082414bf7f8
+oid sha256:ae2e38597c7757459e8233f9c3ff27d2445eb1d0da713d8b5eb49c36d33f3a72
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0bf61cf0d057bf8db7e5742b05c339faebcc7038ea97dc73bda7aee1fbb09c7
+oid sha256:e98ef70cfda45344b059f7fd6f22e58117fb33bd9fb1e0942ef6840fca2f9822
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a37cbe2fd5d44041cacd48fad439e5298ef2fc2ac9fdb757c4af88acea9033f
+oid sha256:f55acabffecfe71816c1cf38ab835a272f062ce61f46ff99d2ee34eba4ecd68a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2a6301db2b5e58d7c810f9f0f35dee18c800d0cef729c658d7f5a962d36075
+oid sha256:73773cdbadae7579ea0445987a6ef1cd08a6a2924f2d011103f0b5b3efe812b5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19030983572468288,
+  "epoch": 0.19962570180910794,
   "eval_steps": 50,
-  "global_step": 143,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1032,6 +1032,63 @@
       "learning_rate": 1.0705439301261887e-06,
       "loss": 45.5314,
       "step": 143
+    },
+    {
+      "epoch": 0.1916406737367436,
+      "grad_norm": 5.012913703918457,
+      "learning_rate": 7.870200411711658e-07,
+      "loss": 44.3529,
+      "step": 144
+    },
+    {
+      "epoch": 0.19297151174880434,
+      "grad_norm": 4.687958240509033,
+      "learning_rate": 5.46834442645952e-07,
+      "loss": 45.6731,
+      "step": 145
+    },
+    {
+      "epoch": 0.19430234976086505,
+      "grad_norm": 4.852694988250732,
+      "learning_rate": 3.501273961763529e-07,
+      "loss": 43.5008,
+      "step": 146
+    },
+    {
+      "epoch": 0.19563318777292577,
+      "grad_norm": 4.63925838470459,
+      "learning_rate": 1.9701377313817158e-07,
+      "loss": 45.8929,
+      "step": 147
+    },
+    {
+      "epoch": 0.19696402578498648,
+      "grad_norm": 4.218976020812988,
+      "learning_rate": 8.758298757550186e-08,
+      "loss": 45.9191,
+      "step": 148
+    },
+    {
+      "epoch": 0.1982948637970472,
+      "grad_norm": 5.067894458770752,
+      "learning_rate": 2.1898943985529384e-08,
+      "loss": 46.9714,
+      "step": 149
+    },
+    {
+      "epoch": 0.19962570180910794,
+      "grad_norm": 5.027199745178223,
+      "learning_rate": 0.0,
+      "loss": 46.4302,
+      "step": 150
+    },
+    {
+      "epoch": 0.19962570180910794,
+      "eval_loss": 1.4293036460876465,
+      "eval_runtime": 573.7255,
+      "eval_samples_per_second": 4.412,
+      "eval_steps_per_second": 2.207,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -1046,12 +1103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.072804944199025e+17,
+  "total_flos": 8.47874607229698e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null