Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a3468cb9537364eaba686d7ffd210630ee5d952e175464adc9e42d792d7e45
+oid sha256:6dc2215651725a2125a334164bb0b6980ccade9e46bd1f4664c523144007cb55
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7ef507bf8a1035e205fd3beb7ec3e3c7e30de0f6733a0ba8cb3b952377e695
+oid sha256:481ef056bda073c57f94ed655d104eae93deef1bdbf35a29e828fb6f653c2fcf
 size 31822948

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6246ae0450cb10a431b2bab716d887ae6218ceb03d1beb34e40792d1de44d94
+oid sha256:69b145fda89fae3e485800133622d555bc54ad50be52f29c1dc4f6884c5debec
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a38ebb80a22f29ce15b98e23c05e06ae87d1dafc271011668fdeb89ab7a129
+oid sha256:c1a4a46d143de27ff269ea4e7eba147693b1e20a00a78905d2214af1093b0997
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505008d2f6dcdcae56c95b8999b09b0595ac016a54da75373600b7a54787f0db
+oid sha256:2b66f1a31b4ab05b86012e363cd2cd54a45379a5956f3394f58d32c80549e45c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6bc6b30ecb556ed465cd8e004650fdea63081c2381798d28a3c4f4543f1f3d
+oid sha256:9e43054cc7538c7e924e55826fcc46a64627fa80294d54da93a85856c2fb2ea0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.681044267877412,
+  "epoch": 0.9080590238365494,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 87.199,
       "eval_steps_per_second": 11.047,
       "step": 150
+    },
+    {
+      "epoch": 0.7037457434733257,
+      "grad_norm": 0.2579304873943329,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 1.1115,
+      "step": 155
+    },
+    {
+      "epoch": 0.7264472190692395,
+      "grad_norm": 0.22793807089328766,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 1.1064,
+      "step": 160
+    },
+    {
+      "epoch": 0.7491486946651532,
+      "grad_norm": 0.24374108016490936,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 1.0788,
+      "step": 165
+    },
+    {
+      "epoch": 0.771850170261067,
+      "grad_norm": 0.26872718334198,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 1.125,
+      "step": 170
+    },
+    {
+      "epoch": 0.7945516458569807,
+      "grad_norm": 0.24592474102973938,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 1.1343,
+      "step": 175
+    },
+    {
+      "epoch": 0.8172531214528944,
+      "grad_norm": 0.2573363184928894,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.1591,
+      "step": 180
+    },
+    {
+      "epoch": 0.8399545970488081,
+      "grad_norm": 0.254545122385025,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 1.121,
+      "step": 185
+    },
+    {
+      "epoch": 0.8626560726447219,
+      "grad_norm": 0.2911272346973419,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 1.1365,
+      "step": 190
+    },
+    {
+      "epoch": 0.8853575482406356,
+      "grad_norm": 0.2981671690940857,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 1.1286,
+      "step": 195
+    },
+    {
+      "epoch": 0.9080590238365494,
+      "grad_norm": 0.2607629597187042,
+      "learning_rate": 0.0,
+      "loss": 1.1407,
+      "step": 200
+    },
+    {
+      "epoch": 0.9080590238365494,
+      "eval_loss": 1.0933903455734253,
+      "eval_runtime": 4.2232,
+      "eval_samples_per_second": 87.849,
+      "eval_steps_per_second": 11.129,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -263,12 +341,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.261560129342669e+16,
+  "total_flos": 1.1007414728707277e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null