Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
     "q_proj",
-    "o_proj"
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca95899caa6de95651e6257cc01a5e2e984bd203d1c78ef702e95910ed938831
+oid sha256:3b847b81553b1a4c390994b0062736795b89f67e6e7dbc41470f32f60ba0cc00
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3b65e8bbc7ea2c93ac43da37dedfcecfc3d46c5e271ded74043f189fc66f906
+oid sha256:379994623b78bf863f8ce9d1409f855c166d168283dc1d592284ff83a7162afd
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0d195e82f6ab52aecb5e6d9128fa3a2715048e13e58720720b2a9ee160b823
+oid sha256:45267a69bd3652f163ea987049746b333392bbe6566ee14654ce77ec1c48934c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,110 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006072874493927126,
+  "epoch": 0.0005060728744939271,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0002249212775528565,
-      "eval_loss": NaN,
-      "eval_runtime": 849.7533,
-      "eval_samples_per_second": 8.812,
-      "eval_steps_per_second": 1.101,
+      "epoch": 5.623031938821413e-05,
+      "eval_loss": 1.2098013162612915,
+      "eval_runtime": 289.309,
+      "eval_samples_per_second": 25.882,
+      "eval_steps_per_second": 12.941,
       "step": 1
     },
     {
-      "epoch": 0.0006747638326585695,
-      "grad_norm": NaN,
-      "learning_rate": 3e-05,
-      "loss": 0.0,
-      "step": 3
-    },
-    {
-      "epoch": 0.001349527665317139,
-      "grad_norm": NaN,
-      "learning_rate": 6e-05,
-      "loss": 0.0,
-      "step": 6
-    },
-    {
-      "epoch": 0.0020242914979757085,
-      "grad_norm": NaN,
-      "learning_rate": 9e-05,
-      "loss": 0.0,
-      "step": 9
-    },
-    {
-      "epoch": 0.0020242914979757085,
-      "eval_loss": NaN,
-      "eval_runtime": 723.8182,
-      "eval_samples_per_second": 10.345,
-      "eval_steps_per_second": 1.293,
+      "epoch": 0.0005060728744939271,
+      "eval_loss": 0.9007603526115417,
+      "eval_runtime": 289.7759,
+      "eval_samples_per_second": 25.841,
+      "eval_steps_per_second": 12.92,
       "step": 9
-    },
-    {
-      "epoch": 0.002699055330634278,
-      "grad_norm": NaN,
-      "learning_rate": 9.987820251299122e-05,
-      "loss": 0.0,
-      "step": 12
-    },
-    {
-      "epoch": 0.0033738191632928477,
-      "grad_norm": NaN,
-      "learning_rate": 9.924038765061042e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.004048582995951417,
-      "grad_norm": NaN,
-      "learning_rate": 9.806308479691595e-05,
-      "loss": 0.0,
-      "step": 18
-    },
-    {
-      "epoch": 0.004048582995951417,
-      "eval_loss": NaN,
-      "eval_runtime": 735.0797,
-      "eval_samples_per_second": 10.187,
-      "eval_steps_per_second": 1.273,
-      "step": 18
-    },
-    {
-      "epoch": 0.004723346828609987,
-      "grad_norm": NaN,
-      "learning_rate": 9.635919272833938e-05,
-      "loss": 0.0,
-      "step": 21
-    },
-    {
-      "epoch": 0.005398110661268556,
-      "grad_norm": NaN,
-      "learning_rate": 9.414737964294636e-05,
-      "loss": 0.0,
-      "step": 24
-    },
-    {
-      "epoch": 0.006072874493927126,
-      "grad_norm": NaN,
-      "learning_rate": 9.145187862775209e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.006072874493927126,
-      "eval_loss": NaN,
-      "eval_runtime": 811.8683,
-      "eval_samples_per_second": 9.223,
-      "eval_steps_per_second": 1.153,
-      "step": 27
     }
   ],
-  "logging_steps": 3,
+  "logging_steps": 10,
   "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
@@ -121,8 +42,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.796899292879258e+16,
-  "train_batch_size": 8,
+  "total_flos": 1801769340370944.0,
+  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33659f9d8b30c03b43b74679cc7f4c64be481762eb473655f342f86879a78e56
+oid sha256:6d53d1cee1f7d83a763aa2324144c3393a565873ad492da03db1cb40ba0d0d82
 size 6776