Training in progress, step 153, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c87b15f36b81c5771744e3848e2cdd7e46e29d4a7555f5c16cee7aed4f179f
+oid sha256:b745462f26110d8f5e6c0bcef91055e14492965f4fda21faf63549fad0fcc448
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b4b10f5005e7a8b6f4ef7581dc4126c0128527231b5202113db9bfacecb9be
+oid sha256:aedeeacab12f5e39f365b4749f7ef795c5b68cd1bab0b91369367d075cadfc66
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c985768cd88156b279865b4af398ed65c42e2eb474c28476bc122fd2d648fd1
+oid sha256:afb210574debeca01beef086494f1b0da6d8ee8853b3831ec7094b554157981c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aeb1fbb5e964bbc83fa43b049054867ad1faca8f43271132d241ae074069d5d
+oid sha256:e76ff8614026ec7c5c2d9793615ca4e2f707e550ce0b5a4376af475431afe3f1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6302679217958002,
+  "epoch": 0.7090514120202752,
   "eval_steps": 50,
-  "global_step": 136,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -983,6 +983,133 @@
       "learning_rate": 4.212216399081918e-05,
       "loss": 0.2116,
       "step": 136
+    },
+    {
+      "epoch": 0.634902244750181,
+      "grad_norm": 1.092250943183899,
+      "learning_rate": 4.095071251953399e-05,
+      "loss": 0.2411,
+      "step": 137
+    },
+    {
+      "epoch": 0.6395365677045619,
+      "grad_norm": 1.3056756258010864,
+      "learning_rate": 3.978963279105821e-05,
+      "loss": 0.3435,
+      "step": 138
+    },
+    {
+      "epoch": 0.6441708906589428,
+      "grad_norm": 1.1005077362060547,
+      "learning_rate": 3.863927848152472e-05,
+      "loss": 0.2612,
+      "step": 139
+    },
+    {
+      "epoch": 0.6488052136133237,
+      "grad_norm": 1.237870454788208,
+      "learning_rate": 3.750000000000001e-05,
+      "loss": 0.3284,
+      "step": 140
+    },
+    {
+      "epoch": 0.6534395365677046,
+      "grad_norm": 1.3307782411575317,
+      "learning_rate": 3.637214438174593e-05,
+      "loss": 0.2536,
+      "step": 141
+    },
+    {
+      "epoch": 0.6580738595220854,
+      "grad_norm": 1.4346413612365723,
+      "learning_rate": 3.525605518250964e-05,
+      "loss": 0.2911,
+      "step": 142
+    },
+    {
+      "epoch": 0.6627081824764663,
+      "grad_norm": 1.2083615064620972,
+      "learning_rate": 3.415207237387297e-05,
+      "loss": 0.233,
+      "step": 143
+    },
+    {
+      "epoch": 0.6673425054308472,
+      "grad_norm": 1.4748581647872925,
+      "learning_rate": 3.3060532239693994e-05,
+      "loss": 0.319,
+      "step": 144
+    },
+    {
+      "epoch": 0.6719768283852281,
+      "grad_norm": 1.2144207954406738,
+      "learning_rate": 3.198176727367156e-05,
+      "loss": 0.1959,
+      "step": 145
+    },
+    {
+      "epoch": 0.676611151339609,
+      "grad_norm": 1.5745162963867188,
+      "learning_rate": 3.091610607806452e-05,
+      "loss": 0.3077,
+      "step": 146
+    },
+    {
+      "epoch": 0.6812454742939898,
+      "grad_norm": 1.1295483112335205,
+      "learning_rate": 2.986387326359637e-05,
+      "loss": 0.2328,
+      "step": 147
+    },
+    {
+      "epoch": 0.6858797972483708,
+      "grad_norm": 1.218430757522583,
+      "learning_rate": 2.8825389350575624e-05,
+      "loss": 0.2504,
+      "step": 148
+    },
+    {
+      "epoch": 0.6905141202027516,
+      "grad_norm": 1.1782724857330322,
+      "learning_rate": 2.78009706712622e-05,
+      "loss": 0.2519,
+      "step": 149
+    },
+    {
+      "epoch": 0.6951484431571325,
+      "grad_norm": 1.3294053077697754,
+      "learning_rate": 2.6790929273509545e-05,
+      "loss": 0.249,
+      "step": 150
+    },
+    {
+      "epoch": 0.6951484431571325,
+      "eval_loss": 0.25855064392089844,
+      "eval_runtime": 135.0303,
+      "eval_samples_per_second": 5.384,
+      "eval_steps_per_second": 2.696,
+      "step": 150
+    },
+    {
+      "epoch": 0.6997827661115134,
+      "grad_norm": 0.8559562563896179,
+      "learning_rate": 2.579557282571196e-05,
+      "loss": 0.1331,
+      "step": 151
+    },
+    {
+      "epoch": 0.7044170890658943,
+      "grad_norm": 1.5178470611572266,
+      "learning_rate": 2.4815204523085654e-05,
+      "loss": 0.3093,
+      "step": 152
+    },
+    {
+      "epoch": 0.7090514120202752,
+      "grad_norm": 1.3319201469421387,
+      "learning_rate": 2.385012299531262e-05,
+      "loss": 0.3123,
+      "step": 153
     }
   ],
   "logging_steps": 1,
@@ -1002,7 +1129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.116593719550935e+17,
+  "total_flos": 9.131167934494802e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null