Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269996fcab08a2f4f94ec052c87d3ea3d36bcb29458882ad89976ae8f9f2aebf
+oid sha256:3195b59df0319bb25793fdc2dbee92e9399e08fbf7cba85359a7f313d6ab0732
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7de1f0d9e9f0f45f1bca85d5b8a148c9767010beae89c60f4921b0ab047d0e
+oid sha256:4d11358ee78281cc475ce26e6ec321b3c36fc19caeefd8090fd39d5f20ec1d8c
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea8f7f08c1457da8c5bf37ac83534ada46cebeccf1245fa025799c3111fc0c8
+oid sha256:b80154dda4d1e26b5c238ed392edfb199cd3f14d165048a87e632105bfed136f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
+oid sha256:2188426f4adaa3a6124c181a61860e824dc2136981845a9e9c4162d0d3700af6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06561619351513756,
+  "epoch": 0.07017774707501344,
   "eval_steps": 50,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1348,6 +1348,105 @@
       "learning_rate": 1.9222451411073645e-06,
       "loss": 0.0198,
       "step": 187
+    },
+    {
+      "epoch": 0.06596708225051262,
+      "grad_norm": 2.473052740097046,
+      "learning_rate": 1.6389299449645733e-06,
+      "loss": 0.06,
+      "step": 188
+    },
+    {
+      "epoch": 0.0663179709858877,
+      "grad_norm": 2.1388607025146484,
+      "learning_rate": 1.3779612414252017e-06,
+      "loss": 0.0624,
+      "step": 189
+    },
+    {
+      "epoch": 0.06666885972126275,
+      "grad_norm": 4.802859306335449,
+      "learning_rate": 1.1394185240843983e-06,
+      "loss": 0.1375,
+      "step": 190
+    },
+    {
+      "epoch": 0.06701974845663783,
+      "grad_norm": 1.2416613101959229,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.0575,
+      "step": 191
+    },
+    {
+      "epoch": 0.06737063719201289,
+      "grad_norm": 1.5825155973434448,
+      "learning_rate": 7.298948443822228e-07,
+      "loss": 0.0487,
+      "step": 192
+    },
+    {
+      "epoch": 0.06772152592738796,
+      "grad_norm": 1.4066219329833984,
+      "learning_rate": 5.590386269008512e-07,
+      "loss": 0.0221,
+      "step": 193
+    },
+    {
+      "epoch": 0.06807241466276302,
+      "grad_norm": 0.9604626893997192,
+      "learning_rate": 4.108578473795032e-07,
+      "loss": 0.0109,
+      "step": 194
+    },
+    {
+      "epoch": 0.0684233033981381,
+      "grad_norm": 3.046772003173828,
+      "learning_rate": 2.8539764311908407e-07,
+      "loss": 0.1035,
+      "step": 195
+    },
+    {
+      "epoch": 0.06877419213351317,
+      "grad_norm": 0.6813495755195618,
+      "learning_rate": 1.8269623051318515e-07,
+      "loss": 0.0351,
+      "step": 196
+    },
+    {
+      "epoch": 0.06912508086888823,
+      "grad_norm": 3.706075429916382,
+      "learning_rate": 1.027848934069625e-07,
+      "loss": 0.0673,
+      "step": 197
+    },
+    {
+      "epoch": 0.0694759696042633,
+      "grad_norm": 1.670214295387268,
+      "learning_rate": 4.568797356781784e-08,
+      "loss": 0.0367,
+      "step": 198
+    },
+    {
+      "epoch": 0.06982685833963836,
+      "grad_norm": 3.3166918754577637,
+      "learning_rate": 1.142286327065478e-08,
+      "loss": 0.0824,
+      "step": 199
+    },
+    {
+      "epoch": 0.07017774707501344,
+      "grad_norm": 2.0596609115600586,
+      "learning_rate": 0.0,
+      "loss": 0.0564,
+      "step": 200
+    },
+    {
+      "epoch": 0.07017774707501344,
+      "eval_loss": 0.0022071050480008125,
+      "eval_runtime": 899.1443,
+      "eval_samples_per_second": 10.677,
+      "eval_steps_per_second": 5.338,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1362,12 +1461,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.834525930805002e+17,
+  "total_flos": 1.0518209551663104e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null