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:efa521481053ce5aab8cd93cf69f3c29f2da35a8a3776897cd31eaa406f47a63
+oid sha256:1749ade8c756bb6e89201b8f861f3e6d6c2c5ca34b24ee31b0cdcacfdfb4531b
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b562c5c2fb49363b3a50dfc48b35dd12e996f0ef6e7ad07e14c7a7b3c62891b
+oid sha256:14fe98ab187bdbaa5926a17bc0799e4ece51281bc83c95ac6a3578fa67c6052b
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2925b76675978f2a003af49e60bad6d03101b7295cd960e3da59d2f06feec23
+oid sha256:e3c3cef82a77b8c5738ee503d413c0a4f9866d1a3db207e359a45ff19926f30c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004276519768212628,
+  "epoch": 0.012829559304637885,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,92 @@
       "eval_samples_per_second": 34.607,
       "eval_steps_per_second": 17.307,
       "step": 50
+    },
+    {
+      "epoch": 0.005131823721855154,
+      "grad_norm": 4.736423969268799,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 8.2631,
+      "step": 60
+    },
+    {
+      "epoch": 0.00598712767549768,
+      "grad_norm": 3.9354634284973145,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.4239,
+      "step": 70
+    },
+    {
+      "epoch": 0.006842431629140206,
+      "grad_norm": 5.779056072235107,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 8.0989,
+      "step": 80
+    },
+    {
+      "epoch": 0.007697735582782732,
+      "grad_norm": 5.675789833068848,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 8.2106,
+      "step": 90
+    },
+    {
+      "epoch": 0.008553039536425257,
+      "grad_norm": 5.744926452636719,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 8.2246,
+      "step": 100
+    },
+    {
+      "epoch": 0.008553039536425257,
+      "eval_loss": 2.0408310890197754,
+      "eval_runtime": 142.0789,
+      "eval_samples_per_second": 34.65,
+      "eval_steps_per_second": 17.328,
+      "step": 100
+    },
+    {
+      "epoch": 0.009408343490067783,
+      "grad_norm": 5.404253005981445,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 7.483,
+      "step": 110
+    },
+    {
+      "epoch": 0.010263647443710309,
+      "grad_norm": 7.058231830596924,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 8.0571,
+      "step": 120
+    },
+    {
+      "epoch": 0.011118951397352835,
+      "grad_norm": 5.664774417877197,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 8.5309,
+      "step": 130
+    },
+    {
+      "epoch": 0.01197425535099536,
+      "grad_norm": 4.67970085144043,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 7.8239,
+      "step": 140
+    },
+    {
+      "epoch": 0.012829559304637885,
+      "grad_norm": 6.211084365844727,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 7.6217,
+      "step": 150
+    },
+    {
+      "epoch": 0.012829559304637885,
+      "eval_loss": 2.0031981468200684,
+      "eval_runtime": 141.879,
+      "eval_samples_per_second": 34.699,
+      "eval_steps_per_second": 17.353,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -77,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9101065021292544.0,
+  "total_flos": 2.656857995005133e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null