Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "gate",
-    "down_proj",
-    "v_proj",
     "o_proj",
-    "shared_expert_gate",
-    "k_proj",
     "up_proj",
-    "q_proj"
+    "k_proj",
+    "gate",
+    "gate_proj",
+    "shared_expert_gate",
+    "v_proj",
+    "q_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:de5f41085465bd4f26c1744d179fc71eb8dfe03431a876156e5c6ad9c381b2fc
+oid sha256:609f33fb9225090b10f1df737a2361196fba3991033aa0a94fd91740f81f4da9
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022c6c3875ba1cd3592c386e3afdad88b470e4be7bc7ef8614ee14e75ec941dc
+oid sha256:087414286a7ea59cf3bed78ffc3a4c2a685a661ed22fb8371853e48f7784ce91
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca4e2bce515e7a88c44624c36d0bc76daf1fd306e88836f9dc2aaf5f09cd386
+oid sha256:cc4bf9c4f1190745e112de22c0a48a7c29f2de445f4aabf7c40b55516fff102e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015772870662460567,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02050473186119874,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0015772870662460567,
       "eval_loss": 11.935985565185547,
-      "eval_runtime": 39.3763,
-      "eval_samples_per_second": 6.781,
-      "eval_steps_per_second": 3.403,
+      "eval_runtime": 33.1237,
+      "eval_samples_per_second": 8.061,
+      "eval_steps_per_second": 4.045,
       "step": 1
+    },
+    {
+      "epoch": 0.007886435331230283,
+      "grad_norm": 0.20729076862335205,
+      "learning_rate": 5e-05,
+      "loss": 11.9381,
+      "step": 5
+    },
+    {
+      "epoch": 0.015772870662460567,
+      "grad_norm": 0.16789914667606354,
+      "learning_rate": 0.0001,
+      "loss": 11.9335,
+      "step": 10
+    },
+    {
+      "epoch": 0.015772870662460567,
+      "eval_loss": 11.933769226074219,
+      "eval_runtime": 34.0875,
+      "eval_samples_per_second": 7.833,
+      "eval_steps_per_second": 3.931,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 250311868416.0,
+  "total_flos": 2941164453888.0,
   "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 sha256:49d4ac77c3c35b9ec9e2a459c121b8e314f51bc7afca10ccf6f739b167a5f313
+oid sha256:d5fe84cc13cdac14fbd5e264ffcfab437a6c5fd7b2665cb1ee66a4afaad006fb
 size 6776