Training in progress, step 155, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672b05673b812e5e9c2b96e7fc581c47c8bc45fe637a2c64823fa5c26313a4d1
+oid sha256:227adafcb3661e0fe28d53f556ee3284a7d48a5c9a0810bd0fe8807218bd794a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd0849778cac2f59c2171424c9084ba127563d2e4a8b6176002dcd78d4fcb10
+oid sha256:6947a1e336e3a111e46e8a79598a467433fe5357f1354a6f516a06bdf2168e30
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e848e9332425e8f19037f20611574d35f1552d094f74408669d2f10122fbcb5d
+oid sha256:ffe48ebb455ffba72b9860ac12b55136a59656ec0530c165ba27b7c19406f06d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ccd887015d7faf1da47941525d069c3cb7c1208d0267f6e00e06c9dcf3b23ab
+oid sha256:1c3cae664c706985d4c0961fa50b158b73244614fe73909f68a02610f6e833f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0060851926977687,
+  "epoch": 1.2576064908722109,
   "eval_steps": 31,
-  "global_step": 124,
+  "global_step": 155,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -334,6 +334,84 @@
       "eval_samples_per_second": 15.485,
       "eval_steps_per_second": 1.936,
       "step": 124
+    },
+    {
+      "epoch": 1.0223123732251522,
+      "grad_norm": 4.823460578918457,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.8243,
+      "step": 126
+    },
+    {
+      "epoch": 1.0466531440162272,
+      "grad_norm": 3.5276401042938232,
+      "learning_rate": 7.537691814803521e-05,
+      "loss": 1.8807,
+      "step": 129
+    },
+    {
+      "epoch": 1.0709939148073022,
+      "grad_norm": 4.932689189910889,
+      "learning_rate": 7.424048101231686e-05,
+      "loss": 1.6877,
+      "step": 132
+    },
+    {
+      "epoch": 1.0953346855983772,
+      "grad_norm": 4.79948091506958,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 1.675,
+      "step": 135
+    },
+    {
+      "epoch": 1.1196754563894524,
+      "grad_norm": 5.320326328277588,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.8877,
+      "step": 138
+    },
+    {
+      "epoch": 1.1440162271805274,
+      "grad_norm": 5.259227752685547,
+      "learning_rate": 7.073466213281196e-05,
+      "loss": 1.7584,
+      "step": 141
+    },
+    {
+      "epoch": 1.1683569979716024,
+      "grad_norm": 3.7490923404693604,
+      "learning_rate": 6.953655642446368e-05,
+      "loss": 1.6734,
+      "step": 144
+    },
+    {
+      "epoch": 1.1926977687626774,
+      "grad_norm": 5.446073532104492,
+      "learning_rate": 6.832506133621487e-05,
+      "loss": 1.9009,
+      "step": 147
+    },
+    {
+      "epoch": 1.2170385395537526,
+      "grad_norm": 4.892331600189209,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.7449,
+      "step": 150
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 5.024781227111816,
+      "learning_rate": 6.586523282025462e-05,
+      "loss": 1.7636,
+      "step": 153
+    },
+    {
+      "epoch": 1.2576064908722109,
+      "eval_loss": 0.5101395845413208,
+      "eval_runtime": 13.4502,
+      "eval_samples_per_second": 15.464,
+      "eval_steps_per_second": 1.933,
+      "step": 155
     }
   ],
   "logging_steps": 3,
@@ -353,7 +431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.646904300577751e+17,
+  "total_flos": 2.059357990598738e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null